Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, non-destructive and openWorld, so the safety profile is covered. The description adds a genuinely non-obvious disclosure — the view is 'synthetic' — which tells the agent the data is not authoritative and should be caveated, plus it names the two fields returned. No statement about distance units or resolution, minor.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, zero filler, and the most important clause (what is returned) is front-loaded before the usage hint. Nothing is repeated from the title or schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the return-value burden and does name both returned facts. It is complete enough to call the tool correctly and interpret the result, though it stops short of unit/format detail for the distance and of any sibling disambiguation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%: country, language, latitude and longitude each carry format examples and range bounds. The description adds nothing about parameter semantics, so the baseline of 3 applies when the schema does all the work.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb ('Returns') and resource ('a synthetic accessibility view of a property') and enumerates the payload (public-transport presence, nearest stop distance), which is enough to distinguish it from nearby_pois or location_summary by content. It never names a sibling explicitly, but the output content is specific enough to route correctly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives a concrete usage trigger: 'Use it to answer questions like is this property practical without a car?'. That is clear context for when to reach for this tool, though it offers no exclusions or named alternatives versus yatmo_get_nearby_pois or yatmo_get_location_summary.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is fully covered. The description adds value by disclosing the shape of the response (human-readable summary plus structured facts), but says nothing about latency, caching, or the open-world dependency implied by openWorldHint.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences: the return contract first, then the intended use. Every clause earns its place and nothing is front-loaded incorrectly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description must carry the return-value burden, and it does so at a high level by naming the summary and the specific fact categories. It is nearly complete for a read-only lookup; only the contrast with sibling tools and any format/pagination details are missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all four parameters (latitude, longitude, language, country) are already documented with ranges and example codes. The description adds no parameter-level detail such as coordinate precision or how language/country interact, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource: returns a neighbourhood summary plus structured facts (nearest school, supermarket, transport) around a location. This is clearly distinguishable from a generic POI lookup, though it does not explicitly contrast itself with the overlapping siblings yatmo_get_nearby_pois or yatmo_get_nearest_by_category.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives one contextual use case ('explain why a property is well situated'), which implies usage but offers no when-not conditions and never names an alternative sibling tool. An agent must infer the boundary against yatmo_get_nearby_pois and yatmo_get_nearest_by_category on its own.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds category disambiguation (school vs. nursery) but says nothing about result ordering, truncation behavior, or what happens when the radius yields no matches – gaps the annotations don't fill.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, front-loaded with the core action before the category detail, and no filler. Only mild redundancy between the general 'filtered by category' clause and the subsequent category glossary.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 7-parameter, 4-required geo query with no output schema, the description covers purpose and category semantics but omits the return shape and what fields each POI carries, plus any note on ordering or result-count behavior. Adequate but with clear gaps for a tool whose output the agent must reason about.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3, but the description goes beyond it: it enumerates the valid category tokens and disambiguates two overlapping ones ('school' excludes daycare, 'nursery' is crèches/daycare only). That is real added meaning for a parameter the schema documents only as free-form strings ('Category tokens to keep; empty = all') with no enum. It does not add anything on radiusMeters/maxResults, but the schema's capping notes suffice there.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Specific verb and resource: 'Lists points of interest around a property' with the optional category filter and radius scoping stated up front. It does not, however, name or contrast itself with the sibling tools (yatmo_get_nearest_by_category, yatmo_get_location_summary), so the reader can't tell from the text alone which tool to pick for a proximity query.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains what can be filtered but never states when to use this tool versus yatmo_get_nearest_by_category or yatmo_get_accessibility_profile, which are clearly adjacent in scope. No prerequisites, no when-not-to-use guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, open-world and non-destructive behavior, so the safety profile is covered. The description adds genuinely useful context beyond them: the result is a single point and it includes distance and travel time, which matters because there is no output schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences with the primary behavior front-loaded and the category list last. Minor redundancy: the category values repeat what is already in the category parameter description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a five-parameter required-input lookup with no output schema, the description usefully discloses that the response carries distance and travel time. It does not explain how language/country affect results, but nothing critical to calling it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so all five parameters including units and ranges are already documented in the schema. The description's category list largely duplicates the schema's category description and adds no format or semantics beyond it, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource with a clear scope qualifier: 'the single nearest point of interest of a given category.' The word 'single' implicitly separates it from the plural sibling yatmo_get_nearby_pois, but no sibling is named explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The category enumeration hints at when the tool applies, and 'single nearest' suggests a one-result use case, but there is no explicit guidance on when to choose this over yatmo_get_nearby_pois or yatmo_get_accessibility_profile, nor any stated preconditions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.